人-信息-物理协同下核电设备可演进式剩余寿命估计

doi:10.3901/JME.2025.04.302

机械工程学报 ›› 2025, Vol. 61 ›› Issue (4): 302-313.doi: 10.3901/JME.2025.04.302

• 交叉与前沿 • 上一篇

扫码分享

人-信息-物理协同下核电设备可演进式剩余寿命估计

蒋翔宇¹, 冯毅雄^1,2, 张志峰¹, 宋秀菊¹, 洪兆溪^1,3, 胡炳涛¹, 谭建荣¹

1. 浙江大学流体动力基础件与机电系统全国重点实验室杭州 310027;
2. 贵州大学省部共建公共大数据国家重点实验室贵阳 550025;
3. 浙江大学宁波科创中心宁波 315100

收稿日期:2024-05-09 修回日期:2024-10-23 发布日期:2025-04-14
作者简介:蒋翔宇，女，1997年出生，博士研究生。主要研究方向为复杂装备寿命预测与健康管理等。E-mail：11925071@zju.edu.cn
冯毅雄(通信作者)，男，1975年出生，博士，教授，博士研究生导师。主要研究方向为现代设计理论与方法等。E-mail：fyxtv@zju.edu.cn
张志峰，男，1991年出生，博士研究生。主要研究方向为绿色设计理论与智能调度等。E-mail：zhzhfeng@zju.edu.cn
宋秀菊，女，1989年出生，博士，研究员，博士研究生导师。主要研究方向为材料结构设计驱动的高性能器件制造等。E-mail：songxiuju@zju.edu.cn
洪兆溪，女，1990年出生，博士，助理研究员。主要研究方向为智能设计与不确定性优化决策。E-mail：hzhx@zju.edu.cn
胡炳涛，男，1992年出生，博士，副研究员。主要研究方向为产品设计理论与智能制造。E-mail：hubingtao@zju.edu.cn
谭建荣，男，1954年出生，博士，教授，博士研究生导师，中国工程院院士。主要研究方向为CAX方法学、工程图学、企业信息化。E-mail：egi@zju.edu.cn
基金资助:
国家重点研发计划(2022YFB3402000)、浙江省重点研发计划(2024C01207)和国家自然科学基金(52105281，52205288)资助项目。

Evolvable Remaining Useful Life Estimation of Nuclear Power Equipment Under Human-cyber-physical Collaboration

JIANG Xiangyu¹, FENG Yixiong^1,2, ZHANG Zhifeng¹, SONG Xiuju¹, HONG Zhaoxi^1,3, HU Bingtao¹, TAN Jianrong¹

1. State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027;
2. State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025;
3. Ningbo Innovation Center, Zhejiang University, Ningbo 315100

Received:2024-05-09 Revised:2024-10-23 Published:2025-04-14

摘要/Abstract

摘要： 在工业5.0新时代，将设备物理实体与人类认知、信息技术融合，是推动故障预测与健康管理(Prognostics and health management, PHM)智能增强的重要途径，剩余寿命估计作为PHM中的关键环节，为设备预测性维护提供时间裕量依据。受人的记忆和遗忘机制启发，提出一种人-信息-物理协同的剩余寿命估计可演进式模型框架，能够同时预测设备的连续状态和离散状态。模型采用基于实例的学习策略从时序数据中汲取并保留知识，无须事先假设固定的失效阈值和退化阶段，旨在随着样本的加入而逐渐调整趋于稳定，适合于设备小样本和先验知识不足的情况，或设备处于变化的运行环境中。模型底层采用核最小均方算法，使模型结构和参数可以在线更新；基于最近实例质心估计方法改进算法，将输入空间拓展为特征空间，随着输入数据的学习将空间自动划分为不同子区域，以实现在预测未来信号的同时获取健康状态信息，进而推导剩余寿命。为了使模型网络规模更加紧凑，引入在线矢量量化方法，通过消除模型冗余的基函数降低计算复杂度。将所提模型框架运用于某压水堆给水泵剩余寿命估计，验证了方法的有效性。

关键词: 人-信息-物理协同, 剩余寿命, 同步预测, 核最小方均

Abstract: In the new era of Industry 5.0, the integration of physical entities of equipment with human cognition and information technology is an important way to promote the intelligent of prognostics and health management(PHM). The estimation of residual life is a key link in PHM. It is the basis for the predictive maintenance of equipment. Inspired by the human memory and forgetting mechanism, an evolvable model framework of human-cyber-physical collaboration for remaining useful life estimation is proposed, which can simultaneously predict the continuous state and discrete state of the equipment. The model adopts instance-based learning to absorb and retain knowledge from time series data without assuming a fixed failure threshold and degradation stage in advance. The model aims to gradually adjust and become stable with incremental samples, which is suitable for the equipment with small-scale samples and insufficient prior knowledge, or the equipment in a changing operating environment. The kernel least mean square (KLMS) algorithm is used adapted as the underlying algorithm so that the model structure and parameters could be updated online. After KLMS expands the input space into a feature space, the nearest-instance centroid estimation(NICE) is used to improve it by automatically dividing the feature space into different sub-regions with the input data learning, to realize the prediction of future signals and obtain health status information at the same time. Then the remaining useful life is derived. In order to make the model network more compact, the online modified vector quantization(M-VQ) method is introduced to reduce the computational complexity by eliminating redundant basis functions of the model. The proposed model framework is applied to estimate the remaining life of the feed pump in a pressurized water reactor, and the effectiveness of the method is verified.

Key words: human-cyber-physical collaboration, remaining useful life, synchronous prediction, kernel least mean square

中图分类号:

TG156

蒋翔宇, 冯毅雄, 张志峰, 宋秀菊, 洪兆溪, 胡炳涛, 谭建荣. 人-信息-物理协同下核电设备可演进式剩余寿命估计[J]. 机械工程学报, 2025, 61(4): 302-313.

JIANG Xiangyu, FENG Yixiong, ZHANG Zhifeng, SONG Xiuju, HONG Zhaoxi, HU Bingtao, TAN Jianrong. Evolvable Remaining Useful Life Estimation of Nuclear Power Equipment Under Human-cyber-physical Collaboration[J]. Journal of Mechanical Engineering, 2025, 61(4): 302-313.

参考文献

[1] GUO Jian，LI Zhaojun，LI Meiyan. A review on prognostics methods for engineering systems[J]. IEEE Transactions on Reliability，2020，69(3):1110-1129.
[2] 李乃鹏，蔡潇，雷亚国，等. 一种融合多传感器数据的数模联动机械剩余寿命预测方法[J]. 机械工程学报，2021，57(20):29-37，46. LI Naipeng，CAI Xiao，LEI Yaguo，et al. A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery[J]. Journal of Mechanical Engineering，2021，57(20):29-37，46.
[3] SOLEIMANI M，FAIZ J，NASAB P S，et al. Temperature measuring-based decision-making prognostic approach in electric power transformers winding failures[J]. IEEE Transactions on Instrumentation and Measurement，2020，69(9):6995-7003.
[4] HU Changhua，PEI Hong，SI Xiaosheng，et al. A prognostic model based on DBN and diffusion process for degrading bearing[J]. IEEE Transactions on Industrial Electronics，2020，67(10):8767-8777.
[5] LING M H，NG H K T，TSUI K L. Bayesian and likelihood inferences on remaining useful life in two-phase degradation models under gamma process[J]. Reliability Engineering & System Safety，2019，184:77-85.
[6] MA Qiuhui，ZHENG Ying，YANG Weidong，et al. Remaining useful life prediction of lithium battery based on capacity regeneration point detection[J]. Energy，2021，234:121233.
[7] ZHANG Yixing，FENG Fei，WANG Shunli，et al. Joint nonlinear-drift-driven Wiener process-Markov chain degradation switching model for adaptive online predicting lithium-ion battery remaining useful life[J]. Applied Energy，2023，341:121043.
[8] LIU Zhenyu，LIU Hui，JIA Weiqiang，et al. A multi-head neural network with unsymmetrical constraints for remaining useful life prediction[J]. Advanced Engineering Informatics，2021，50:101396.
[9] ZHANG Yuhan，YANG Ying，LI He，et al. A data-driven modeling method for stochastic nonlinear degradation process with application to RUL estimation[J]. IEEE Transactions on Systems，Man，and Cybernetics:Systems，2022，52(6):3847-3858.
[10] HU Kui，CHENG Yiwei，WU Jun，et al. Deep bidirectional recurrent neural networks ensemble for remaining useful life prediction of aircraft engine[J]. IEEE Transactions on Cybernetics，2023，53(4):2531-2543.
[11] PRAKASH O，SAMANTARAY A K. Prognosis of dynamical system components with varying degradation patterns using model-data-fusion[J]. Reliability Engineering & System Safety，2021，213:107683.
[12] AL-DULAIMI A，ZABIHI S，ASIF A，et al. A multimodal and hybrid deep neural network model for remaining useful life estimation[J]. Computers in Industry，2019，108:186-196.
[13] LI Zhixiong，WU Dazhong，HU Chao，et al. An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction[J]. Reliability Engineering & System Safety，2019，184:110-122.
[14] XIA Pengcheng，HUANG Yixiang，LI Peng，et al. Fault knowledge transfer assisted ensemble method for remaining useful life prediction[J]. IEEE Transactions on Industrial Informatics，2022，18(3):1758-1769.
[15] JIANG Xiangyu，FENG Yixiong，LI Zhiwu，et al. Hierarchical data fusion-based health state assessment of nuclear power plant operation under human-cyber-physical system architecture[J]. IEEE Transactions on Automation Science and Engineering，2023，22:523-533.
[16] FENG Yixiong，JIANG Xiangyu，HONG Zhaoxi，et al. Human-cyber-physical system for operation in nuclear reactor possessing asymmetric multi-task learning-based predicting framework[J]. Journal of Manufacturing Systems，2022，64:443-453.
[17] YANG Lingxiao，SUN Qiuye，ZHANG Ning，et al. Optimal energy operation strategy for we-energy of energy internet based on hybrid reinforcement learning with human-in-the-loop[J]. IEEE Transactions on Systems，Man，and Cybernetics:Systems，2022，52(1):32-42.
[18] CHEN Xiao，EDER M A，SHIHAVUDDIN A，et al. A human-cyber-physical system toward intelligent wind turbine operation and maintenance[J]. Sustainability，2021，13(2):561.
[19] ZHENG Zhong，ZHANG Kaitian，GAO Xiaoqiang. Human-cyber-physical system for production and operation decision optimization in smart steel plants[J]. Science China Technological Sciences，2022，65(2):247-260.
[20] LIU Jie，ZIO E. An adaptive online learning approach for support vector regression:Online-SVR-FID[J]. Mechanical Systems and Signal Processing，2016，76-77:796-809.
[21] LI Xifeng，PENG Libiao，GAO Le，et al. A robust hybrid filtering method for accurate battery remaining useful life prediction[J]. IEEE Access，2019，7:57843-57856.
[22] ZHOU Haowen，HUANG Jinquan，LU Feng，et al. Echo state kernel recursive least squares algorithm for machine condition prediction[J]. Mechanical Systems and Signal Processing，2018，111:68-86.
[23] HU Jiawen，SUN Qiuzhaung，YE Zhisheng，et al. Joint modeling of degradation and lifetime data for rul prediction of deteriorating products[J]. IEEE Transactions on Industrial Informatics，2021，17(7):4521-4531.
[24] MIAO Huihui，LI Bing，SUN Chuang，et al. Joint learning of degradation assessment and RUL prediction for aeroengines via dual-task deep LSTM networks[J]. IEEE Transactions on Industrial Informatics，2019，15(9):5023-5032.
[25] ZHOU Haowen，HUANG Jinquan，LU Feng. Reduced kernel recursive least squares algorithm for aero-engine degradation prediction[J]. Mechanical Systems and Signal Processing，2017，95:446-467.
[26] BAO Rongjing，RONG Haijun，YANG Zhixin，et al. A novel prognostic approach for RUL estimation with evolving joint prediction of continuous and discrete states[J]. IEEE Transactions on Industrial Informatics，2019，15(9):5089-5098.
[27] PARISI G I，KEMKER R，PART J L，et al. Continual lifelong learning with neural networks:A review[J]. Neural Networks:The Official Journal of the International Neural Network Society，2019，113:54-71.
[28] 庞业勇，王少军，彭宇，等. 一种在线时间序列预测的核自适应滤波器向量处理器[J]. 电子与信息学报，2016，38(1):53-62. PANG Yeyong，WANG Shaojun，PENG Yu，et al. A kernel adaptive filter vector processor for online time series prediction[J]. Journal of Electronics & Information Technology，2016，38(1):53-62.
[29] 韩敏，马俊珠，任伟杰，等. 基于核自适应滤波器的时间序列在线预测研究综述[J]. 自动化学报，2021，47(4):730-746. HAN Min，MA Junzhu，REN Weijie，et al. A survey of time series online prediction based on kernel adaptive filters[J]. Acta Automatica Sinica，2021，47(4):730-746.

人-信息-物理协同下核电设备可演进式剩余寿命估计

Evolvable Remaining Useful Life Estimation of Nuclear Power Equipment Under Human-cyber-physical Collaboration

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	朱挺, 陈兆祥, 周笛, 陈震, 胡兵, 潘尔顺. 基于Bayesian-LSTM神经网络的热轧轧辊剩余寿命预测及不确定性评估[J]. 机械工程学报, 2024, 60(11): 181-190.
[2]	王宇, 刘秋发, 彭一真. 非均匀监测条件下滚动轴承剩余寿命预测方法[J]. 机械工程学报, 2023, 59(23): 96-104.
[3]	庞哲楠, 裴洪, 李天梅, 胡昌华, 司小胜. 考虑不完美维修的随机退化设备剩余寿命自适应预测方法[J]. 机械工程学报, 2023, 59(2): 14-29.
[4]	王超, 杨冰, 朱涛, 肖守讷, 阳光武, 范晓达. 表面强化车轴裂纹扩展及剩余寿命预测方法研究[J]. 机械工程学报, 2023, 59(14): 43-53.
[5]	沈天浩, 丁康, 黎杰, 黄如意, 李巍华. 图结构联合时序数据驱动的装备剩余使用寿命预测方法[J]. 机械工程学报, 2023, 59(12): 183-194.
[6]	杨超颖, 刘颉, 周凯波. 基于路图注意力网络的轴承剩余寿命预测方法[J]. 机械工程学报, 2023, 59(12): 195-201.
[7]	郑锐, 周一帆. 针对比例风险退化系统健康评估的迭代算法[J]. 机械工程学报, 2023, 59(10): 366-373.
[8]	马硕, 姜兴宇, 杨国哲, 刘伟军, 乔赫廷, 王子生. 废旧机床主轴剩余寿命评估模型[J]. 机械工程学报, 2021, 57(4): 219-226.
[9]	付洋, 曹宏瑞, 郜伟强, 高文辉. 数字孪生驱动的航空发动机涡轮盘剩余寿命预测[J]. 机械工程学报, 2021, 57(22): 106-113.
[10]	王久健, 杨绍普, 刘永强, 文桂林. 一种基于空间卷积长短时记忆神经网络的轴承剩余寿命预测方法[J]. 机械工程学报, 2021, 57(21): 88-95.
[11]	李乃鹏, 蔡潇, 雷亚国, 徐鹏程, 王文廷, 王彪. 一种融合多传感器数据的数模联动机械剩余寿命预测方法[J]. 机械工程学报, 2021, 57(20): 29-37,46.
[12]	王学远, 李日康, 魏学哲, 戴海峰, 郑岳久. 基于传荷电阻的锂离子电池剩余寿命预测研究[J]. 机械工程学报, 2021, 57(14): 105-117.
[13]	车畅畅, 王华伟, 倪晓梅, 蔺瑞管, 熊明兰. 基于1D-CNN和Bi-LSTM的航空发动机剩余寿命预测[J]. 机械工程学报, 2021, 57(14): 304-312.
[14]	王泽洲, 陈云翔, 蔡忠义, 项华春, 王莉莉. 基于复合非齐次泊松过程的不完美维修设备剩余寿命预测[J]. 机械工程学报, 2020, 56(22): 14-23.
[15]	辛运胜, 董青, 徐格宁. 轨道连接处缺陷对起重机运行冲击系数及疲劳剩余寿命的影响[J]. 机械工程学报, 2020, 56(14): 254-264.